TaskGen: A Task-Based, Memory-Infused Agentic Framework using StrictJSON
John Chong Min Tan, Prince Saroj, Bharat Runwal, Hardik Maheshwari,, Brian Lim Yi Sheng, Richard Cottrill, Alankrit Chona, Ambuj Kumar, Mehul, Motani

TL;DR
TaskGen is a flexible agent framework that breaks down complex tasks into subtasks, uses StrictJSON for efficient communication, and manages memory selectively, achieving high success rates across diverse environments.
Contribution
It introduces TaskGen, a novel task decomposition and memory management framework utilizing StrictJSON for improved efficiency and accuracy in LLM-based agents.
Findings
100% solve rate in maze navigation
96% solve rate in TextWorld escape room
F1 score of 47.03% on NaturalQuestions
Abstract
TaskGen is an open-sourced agentic framework which uses an Agent to solve an arbitrary task by breaking them down into subtasks. Each subtask is mapped to an Equipped Function or another Agent to execute. In order to reduce verbosity (and hence token usage), TaskGen uses StrictJSON that ensures JSON output from the Large Language Model (LLM), along with additional features such as type checking and iterative error correction. Key to the philosophy of TaskGen is the management of information/memory on a need-to-know basis. We empirically evaluate TaskGen on various environments such as 40x40 dynamic maze navigation with changing obstacle locations (100% solve rate), TextWorld escape room solving with dense rewards and detailed goals (96% solve rate), web browsing (69% of actions successful), solving the MATH dataset (71% solve rate over 100 Level-5 problems), Retrieval Augmented…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMulti-Agent Systems and Negotiation
